Abstract
The use of multiprocessor systems in the field of image analysis and understanding is motivated by the huge amount of data and the need for extremly fast processing that is necessary to achieve practical computer vision systems. The development of parallel algorithms for the knowledge-based interpretation of complex scences (patterns) must consider aspects of knowledge representation as well as it’s efficient use. It is complicated by special problems of symbolic image processing, like unreliable segmentation results, variable data dependencies, or the need for integration of different levels of representation.
This paper introduces a parallel control algorithm for an image understanding system that uses semantic networks for the representation of task-specific knowledge. The algorithm is based on an explicit representation of all necessary inferences in a single data flowchart. In a bottom-up instantiation the sensor data are used for the computation of competing instances for each element of the knowledge base. A top-down optimization is used for the iterative improvement and selection of hypotheses.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
D. Ballard and C. Brown. Computer Vision. Prentice Hall, Englewood Cliffs, New Jersey, 1982.
V. Chaudhary and J.K. Aggarwal. Parallelism in computer vision: A review. In V. Kumar, P.S. Gopalakrishnan, and L.N. Kumar, editors, Parallel Algorithms for Machine Intelligence and Vision, pages 271–309. Springer-Verlag, New York, Berlin, Heidelberg, 1990.
P. Dauphin, F. Hartleb, M. Kienow, V. Mertsiotakis, and A. Quick. Pepp: Performance evaluation of parallel programs. users’s guide - version 3.1. Technical Report 5/92, Lehrstuhl für Informatik 7, Friedrich-Alexander-Univerität Erlangen-Nürnberg, September 1992.
V. Fischer. Parallelisierung von Instantiierungsoperationen in semantischen Netzen. In Arbeits-und Ergebnisbericht des Sonderforschungsbereichs 182 “Multiprozessor-und Netzwerkkonfigurationen”. Teilprojekt D1, chapter 5.2, pages 109–136. Erlangen, 1992.
A. Hanson and E. Riseman. Processing cones: A computational structure for scene analysis. In S. Tanimoto and A. Klinger, editors, Structured Computer Vision. Academic Press, New York, 1980.
F. Kummert Flexible Steuerung eines sprachverstehenden Systems mit homogener Wissensbasis, volume 12 of Dissertationen zur Künstlichen Intelligenz. Infix, Sankt Augustin, 1992.
H. Levesque and J. Mylopoulos. A procedural semantics for semantic networks. In N. Findler, editor, Associative Networks, pages 93–121. Academic Press, Inc., New York, 1979.
S. Levitan, C. Weems, A. Hanson, and E. Riseman. The UMASS image understanding architecture. In L. Uhr, editor, Parallel Computer Vision, pages 215–248. Academic Press, Inc., Boston, 1987.
T. Messer, S. Steuer, C. Weighardt, D. Wetzel, A. Winklhofer, and A. Zins. Movie-Projektbeschreibung: Schritthaltende Bildfolgeninterpretation von Fahrszenen. Technical report, Bayerisches Forschungszentrum für Wissensbasierte Systeme (FORWISS) und Bayerische Motorenwerke AG (BMW AG ), 1990.
J. Mylopoulos and H. Levesque. An overview of knowledge representation. In M. Brodie, J. Mylopoulos, and J Schmidt, editors, On Conceptual Modelling: Perspectives from Artificial Intelligence, pages 3–17. Springer-Verlag, Berlin, Heidelberg, New York, 1983.
H. Niemann. Pattern Analysis and Understanding. Springer-Verlag, Berlin, Heidelberg, New York, 1990.
H. Niemann, H. Brünig, R. Salzbrunn, and S. Schröder. Interpretation of industrial scenes by semantic networks. In Proc. of the IAPR Workshop on Machine Vision Applications, pages 39–42, Tokyo, 1990.
H. Niemann, H. Brünig, R. Salzbrunn, and S. Schröder. A knowledge-based vision system for industrial applications. In Machine Vision and Applications, volume 3, pages 201–229. Springer-Verlag, New York, 1990.
H. Niemann, H. Bunke, I. Hofmann, G. Sagerer, F. Wolf, and H. Feistel. A knowledge based system for analysis of gated blood pool studies. IEEE Trans. on Pattern Analysis and Machine Intelligence, 7 (3): 246–259, 1985.
H. Niemann, G. Sagerer, U. Ehrlich, E.G. Schukat-Talamazzini, and F. Kummert. The interaction of word recognition and linguistic processing in speech understanding. In R. De Mori and P. Laface, editors, Recent Advances in Speech and Language Modelling, NATO ASI Series F. Springer-Verlag, Berlin, 1992.
H. Niemann, G. Sagerer, S. Schröder, and F. Kummert. ERNEST: A semantic network system for pattern understanding. IEEE Trans. on Pattern Analysis and Machine Intelligence, 12 (9): 883–905, 1990.
J. Nilsson. Principles of Artificial Intelligence. Springer-Verlag, Berlin, Heidelberg, New York, 1982.
D. Paulus. Objektorientierte Bildverarbeitung. Dissertation, Technische Fakultät der Universität Erlangen-Nürnberg, 1991.
J. Pearl. Heuristics. Intelligent Search Strategies for Computer Problem Solving. Addison-Wesley Publishing Company, Reading, Massachusetts, 1984.
V. Prassana Kumar. Parallel Architectures and Algorithms for Image Understanding. Academic Press, Inc., Boston, 1991.
G. Sagerer. Darstellung und Nutzung von Expertenwissen für ein Bildanalysesystern, volume 104 of Informatik-Fachberichte. Springer-Verlag, Berlin, Heidelberg, New York, 1985.
G. Sagerer. Automatisches Verstehen gesprochener Sprache, volume 74 of Reihe Informatik. B.I. Wissenschaftsverlag, Mannheim, 1990.
G. Sagerer, R. Prechtel, and H.-J. Blickle. Ein System zur automatischen Analyse von Sequenzszintigrammen des Herzens. Der Nuklearmediziner, 3: 137–154, 1990.
L. Shastri. Semantic Networks: An Evidential Formalization and its Connectionist Realization. Pitman and Morgan Kaufmann Publishers, Inc., London and San Mateo, California, 1988.
L. Shastri. Why semantic networks? In J.F. Sowa, editor, Principles of Semantic Networks. Explorations in the Representation of Knowledge, chapter 3, pages 109136. Morgan Kaufmann Publishers, Inc., San Mateo, Ca., 1991.
L. Uhr. Parallel Computer Vision. Academic Press, Inc., Boston, 1987.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Fischer, V., Niemann, H. (1993). Parallelism in a Semantic Network for Image Understanding. In: Bode, A., Dal Cin, M. (eds) Parallel Computer Architectures. Lecture Notes in Computer Science, vol 732. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-21577-7_15
Download citation
DOI: https://doi.org/10.1007/978-3-662-21577-7_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57307-4
Online ISBN: 978-3-662-21577-7
eBook Packages: Springer Book Archive